Nvidia RTX 3090 cloud rental prices
3 providers list the Nvidia RTX 3090, 3 have it in stock. Prices run from $0.07 to $0.22 per GPU hour — the same card, 3.2x apart.
Prices and stock checked 2 hours ago
What it costs you to run
Estimated at the cheapest listed rate of $0.07/GPU/hr (Vast.ai), per GPU, before storage, egress or commitment discounts.
Renting at the median instead of the floor costs you an extra $67 a month per GPU. That is 58% of the bill, for identical silicon.
Every provider renting the Nvidia RTX 3090
Ordered strictly by entry price per GPU hour. Rows above the median are marked. Stock is what the provider reported at our last check, not a guarantee.
| Provider | Country | Configs | Scale | From | Spot | Reserved | Stock | Grab |
|---|---|---|---|---|---|---|---|---|
| Vast.ai | United States of America | 1 | 2x-2x | $0.07 | — | — | In stock | GrabVast.ai — opens the provider's site |
| Lium | — | 1 | 1x-1x | $0.16 | — | — | In stock | GrabLium — opens the provider's site |
| Runpod | United States of America | 2 | 1x-1x | $0.22 | $0.22 | — | In stock | GrabRunpod — opens the provider's site |
Live inventory signal
The Lium marketplace publishes GPU counts, which almost nobody else does. It holds 106 Nvidia RTX 3090 GPUs at $0.16/GPU/hr, with 35% already rented. There is slack at that price today.
All 4 configurations
| Configuration | Provider | Region | VRAM | vCPU | RAM | Billing | Per GPU/hr | Total/hr | Stock |
|---|---|---|---|---|---|---|---|---|---|
| 2x RTX 3090 | Vast.ai | AR | 48 GB | 32 | 63 GB | On-Demand | $0.07 | $0.14 | In stock |
| 1x NVIDIA GeForce RTX 3090 | Lium | — | — | — | — | On-Demand | $0.16 | $0.16 | In stock |
| 1x RTX 3090 | Runpod | — | 24 GB | — | — | On-Demand | $0.22 | $0.22 | In stock |
| 1x RTX 3090 | Runpod | — | 24 GB | — | — | Spot | $0.22 | $0.22 | In stock |
What fits in 24 GB
The question behind most rentals: will the model load. Sized against one Nvidia RTX 3090.
| Model | 16-bit | 8-bit | 4-bit |
|---|---|---|---|
| DeepSeek-V3 DeepSeek · 671B params · 37B active | 1,610 GB 68× · 22 GB free | 805 GB 34× · 11 GB free | 403 GB 17× · 5 GB free |
| Llama 3.1 405B Meta · 405B params | 972 GB 41× · 12 GB free | 486 GB 21× · 18 GB free | 243 GB 11× · 21 GB free |
| Qwen3 235B-A22B Alibaba · 235B params · 22B active | 564 GB 24× · 12 GB free | 282 GB 12× · 6 GB free | 141 GB 6× · 3 GB free |
| Mixtral 8x22B Mistral · 141B params · 39B active | 338 GB 15× · 22 GB free | 169 GB 8× · 23 GB free | 85 GB 4× · 11 GB free |
| Mistral Large 2 Mistral · 123B params | 295 GB 13× · 17 GB free | 148 GB 7× · 20 GB free | 74 GB 4× · 22 GB free |
| gpt-oss-120b OpenAI · 117B params · 5.1B active | 281 GB 12× · 7 GB free | 140 GB 6× · 4 GB free | 70 GB 3× · 2 GB free |
| Qwen2.5 72B Alibaba · 72.7B params | 174 GB 8× · 18 GB free | 87 GB 4× · 9 GB free | 44 GB 2× · 4 GB free |
| Llama 3.3 70B Meta · 70.6B params | 169 GB 8× · 23 GB free | 85 GB 4× · 11 GB free | 42 GB 2× · 6 GB free |
| Qwen3 32B Alibaba · 32.8B params | 79 GB 4× · 17 GB free | 39 GB 2× · 9 GB free | 20 GB 1× · 4 GB free |
| Gemma 2 27B Google · 27.2B params | 65 GB 3× · 7 GB free | 33 GB 2× · 15 GB free | 16 GB 1× · 8 GB free |
| Mistral Small 3 Mistral · 24B params | 58 GB 3× · 14 GB free | 29 GB 2× · 19 GB free | 14 GB 1× · 10 GB free |
| Llama 3.1 8B Meta · 8B params | 19 GB 1× · 5 GB free | 10 GB 1× · 14 GB free | 5 GB 1× · 19 GB free |
Required memory is weights plus 20% for KV cache and runtime at short context; long contexts and large batches need more. Cells tinted green fit on a single Nvidia RTX 3090.
Nvidia RTX 3090 specifications
| Architecture | Ampere |
|---|---|
| Memory per GPU | 24 GB GDDR6X |
| Memory bandwidth | 936 GB/s |
| Release date | Q3 2020 |
| GPU interconnect | NVLink 112 GB/s |
| FP16 / BF16 compute rate | 71.2 TFLOPS (dense), 142.4 with sparsity |
| INT8 compute rate | 284.7 TOPS (dense), 569.4 with sparsity |
| Process node | Samsung 8N |
| Board power | 350 W |
Frequently asked questions
How much does it cost to rent a Nvidia RTX 3090 per hour?
As of September 6, 2026 the Nvidia RTX 3090 rents from $0.07 per GPU per hour at Vast.ai. The median across 3 providers is $0.16 and the dearest listing asks $0.22.
Who is the cheapest Nvidia RTX 3090 provider right now?
Vast.ai at $0.07 per GPU per hour. That is 58% under the median of $0.16, so renting from a mid-priced provider costs you $0.09 an hour more for the same silicon.
What does a Nvidia RTX 3090 cost per month?
At the cheapest listed rate of $0.07 per GPU per hour, one Nvidia RTX 3090 running non-stop for a 730-hour month costs $49. At the median rate it costs $117.
Can I actually get a Nvidia RTX 3090 today?
Yes. 3 of 3 providers reported Nvidia RTX 3090 stock at the last check. The cheapest one with confirmed stock is Vast.ai at $0.07 per GPU per hour.
How much VRAM does the Nvidia RTX 3090 have?
24 GB GDDR6X per board. That holds a model of roughly 9 billion parameters at 16-bit, or about 19 billion at 8-bit, before context and activations.
What architecture is the Nvidia RTX 3090, and when did it launch?
Ampere, released Q3 2020. 3 cloud providers publish a price for it.